prospecting

prospecting is a skill for Claude Code from Doris-Labs/sales-skills. It costs 70 tokens per session (1,609 once invoked), scanned A, original, MIT.

A sales research process for building a ranked list of companies that match your ideal customer profile (ICP). It considers company traits, technology, buying signals, and recent events.

In plain words
What is it for?
Use it to decide which accounts to target next, how well they fit, and which person or role to approach.
Why use it?
It replaces an unsorted list of possible customers with a prioritized list and a reason to contact each one now.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the sales-skills plugin — 30 skills shipped together

Good fit Use it to decide which accounts to target next, how well they fit, and which person or role to approach.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/doris-labs/sales-skills/prospecting
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add Doris-Labs/sales-skills --skill prospecting
Clone the repo
git clone --depth 1 https://github.com/Doris-Labs/sales-skills

Made for: Claude Code.

Or install sales-skills, the plugin that ships this one along with the rest of its 30 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for prospecting

README.md
[![agentmods](https://agentmods.dev/badge/skills/doris-labs/sales-skills/prospecting/github.svg)](https://agentmods.dev/skills/doris-labs/sales-skills/prospecting)
Your own site
<a href="https://agentmods.dev/skills/doris-labs/sales-skills/prospecting"><img src="https://agentmods.dev/badge/skills/doris-labs/sales-skills/prospecting/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for prospecting

Your own site · 80×15
<a href="https://agentmods.dev/skills/doris-labs/sales-skills/prospecting"><img src="https://agentmods.dev/badge/skills/doris-labs/sales-skills/prospecting.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,609 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00070 $0.01609
Opus 5 $0.00035 $0.00805
Sonnet 5 $0.00014 $0.00322
Haiku 4.5 $0.00007 $0.00161

Measured 10d ago against content hash 879be2fdbdc3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

prospecting scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/prospecting/SKILL.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Prospecting

Purpose

Turn a vague "go find more pipeline" into a ranked target list: accounts that match your ICP, scored on fit and intent, ordered by what just happened (the trigger), each with a one-line "why now" and the persona to open with.

Inputs

  • Your ICP definition (or enough to build one: industry, size, geo, tech, motion)
  • What "good" looks like — your best-fit closed-won accounts to pattern-match against
  • Any existing account universe (CRM, territory, list) to work or de-dupe against
  • How many targets you want and over what window

Method

  1. Define / sharpen the ICP filter. Lock the hard filters first — only accounts that pass all of these belong on the list:

    • Firmographic: industry / vertical, employee count, revenue band, geography.
    • Technographic: tools they run that imply fit (CRM, CI, data stack, a competitor's product).
    • Motion: B2B/B2C, sales-led vs PLG, deal size band you can actually win.
    • Disqualifiers: sizes/industries/regions you lose in — exclude up front. Anchor each filter to evidence from won deals, not opinion.
  2. Score each account: Fit × Intent. Two independent axes, then combine.

    • Fit (0–5) — how closely the account resembles your won-deal profile: 5 near-twin of a won account · 3 ICP match, no proof yet · 0 fails a hard filter (drop).
    • Intent (0–5) — observable buying signals, weighted by recency: hiring for the pain you solve, leadership change, funding/M&A, expansion, tech adoption/churn, content/event engagement, inbound touch.
    • Priority score = Fit × Intent. Fit-but-no-intent = nurture; intent-but-no-fit = ignore; high-both = work now. Multiplying (not adding) kills the no-fit-high-noise traps.
  3. Trigger-based prioritization. Among high scorers, order by the freshest, most actionable trigger — a trigger is the reason the email lands this week:

    • Tier A (act now): new exec in the buying role, funding round, layoffs/reorg in your function, public initiative matching your value, switched off a competitor.
    • Tier B (this month): hiring spree in target dept, new product launch, expansion/new market.
    • Tier C (passive): tech-stack fit only, lookalike to a won account, old inbound. Recency decays the trigger — a 6-month-old funding round is Tier C.

Read the full file on GitHub · 114 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 10d ago First seen · 114 lines · 70 tokens per session scan A 879be2fdbdc3

Subscribe to this mod's changes

prospecting is a skill published in the GitHub repository Doris-Labs/sales-skills (3 stars, last pushed 3mo ago), licensed MIT. It adds 70 tokens to every session and 1,609 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.